© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205770
    Prev
    Next
    INDEX
    Explanations

    negation of involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     a
    0.54
     usado
    0.47
    מו
    0.45
    اف
    0.43
     nuevos
    0.41
    زا
    0.40
     in
    0.40
    ă
    0.40
     for
    0.40
    -
    0.40
    POSITIVE LOGITS
     HEALTH
    0.55
     Pubmed
    0.48
    HEALTH
    0.48
     collocation
    0.47
     Nutrient
    0.46
     तिजारत
    0.46
    <unused62>
    0.43
     PubMed
    0.43
    िश्वत
    0.43
     vattum
    0.43
    Activations Density 0.003%

    No Known Activations